1996fanrui commented on code in PR #827: URL: https://github.com/apache/flink-kubernetes-operator/pull/827#discussion_r1596344772
########## flink-autoscaler/src/main/java/org/apache/flink/autoscaler/ScalingMetricCollector.java: ########## @@ -247,17 +249,36 @@ protected JobTopology getJobTopology(JobDetailsInfo jobDetailsInfo) { json, slotSharingGroupIdMap, maxParallelismMap, metrics, finished); } - private void updateKafkaSourceMaxParallelisms(Context ctx, JobID jobId, JobTopology topology) - throws Exception { + private void updateKafkaPulsarSourceMaxParallelisms( + Context ctx, JobID jobId, JobTopology topology) throws Exception { try (var restClient = ctx.getRestClusterClient()) { - var partitionRegex = Pattern.compile("^.*\\.partition\\.\\d+\\.currentOffset$"); + Pattern partitionRegex = + Pattern.compile( + "^.*\\.KafkaSourceReader\\.topic\\.(?<kafkaTopic>.+)\\.partition\\.(?<kafkaId>\\d+)\\.currentOffset$" + + "|^.*\\.PulsarConsumer\\.(?<pulsarTopic>.+)-partition-(?<pulsarId>\\d+)\\..*\\.numMsgsReceived$"); for (var vertexInfo : topology.getVertexInfos().values()) { if (vertexInfo.getInputs().isEmpty()) { var sourceVertex = vertexInfo.getId(); var numPartitions = queryAggregatedMetricNames(restClient, jobId, sourceVertex).stream() - .filter(partitionRegex.asMatchPredicate()) - .count(); + .map( Review Comment: Sorry, I got it from your description: `Since Pulsar Source metrics are related to a single Consumer identifier, a single partition may have multiple consumer identifiers, so some deduplication needs to be done here, grouping by topic and partition ID.` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@flink.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org